Integrating deep reinforcement learning with pointer networks for service request scheduling in edge computing

摘要

With the increasing popularity of edge computing, service providers are more likely to deploy services at the edge of the network to reduce the latency of service requests. However, the resources offered by edge servers are extremely limited compared to those in the cloud. Therefore, a challenging issue in edge computing is how to sufficiently utilize service resources at the edge to satisfy as many service requests as possible. Existing service request scheduling methods mainly use a single optimization objective, e.g., resource utilization or running time. In this paper, the issue of service request scheduling with multiple requests is modeled as a sequential problem, where multiple optimization objectives, including resource utilization, running time, and waiting time, are involved. A reinforcement learning model with pointer networks is proposed to construct scheduling policies. Experiments conducted on three representative real-world datasets show that our proposed approach outperforms several state-of-the-art methods on the three metrics.